Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    repeat steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.91
    j
    0.89
    হ
    0.85
    ді
    0.79
    a
    0.78
    r
    0.77
    დ
    0.76
     energies
    0.76
    до
    0.75
    ৪
    0.75
    POSITIVE LOGITS
     Marbella
    0.84
    .”.
    0.82
     semasa
    0.80
    .).
    0.78
     vaik
    0.77
     WooCommerce
    0.75
    !”.
    0.74
    Clarke
    0.74
     Dubrovnik
    0.74
     उर्फी
    0.73
    Act Density 0.001%

    No Known Activations